ClawHub
Back to skill

Security audit

mailbox.bot

Security checks for vulnerabilities and agentic risk

Overview

The skill clearly provides a remote postal-mail service for agents, and its sensitive capabilities are disclosed with sandbox, cost, and human-approval safeguards.

Install only if you intend to let an agent interact with mailbox.bot. Use sandbox keys first, keep API keys out of prompts/logs, prefer agent-scoped keys with the minimum scopes needed, review dry-run prices before live sends, and require human approval for sensitive mail, legal notices, forwarding, scans, or discard actions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · SKILL.md (reported line 117)May include surrounding context.

md
Credits and cancellation: outbound mail uses prepaid credits. Agents never access Stripe or card data and cannot buy
credits; only a signed-in human adds funds at `billing_url`. On `INSUFFICIENT_CREDITS`, report available, required and
the shortfall, then link `billing_url`. Cancel with `DELETE /v1/mail/{id}` (MCP `cancel_outbound_mail`) while the piece
is still `submitted`; a 409 means it is already printing or mailed and no refund was applied.

Tracking: `GET /v1/mail/{id}` returns status, carrier tracking and `fulfillment_photos` (pages, envelope, receipt,

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
92% confidence
Finding

The README instructs users to run npx skills add arbengine/mailbox-bot-skill without pinning a specific package version or immutable source. This creates a supply-chain risk: a future compromised or maliciously updated package under that name could be installed and executed by users or agents, and because this skill handles postal actions, API credentials, and potentially sensitive mail workflows, compromise could expose secrets or trigger unauthorized actions.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 138)May include surrounding context.

  1. Reads. Search senders, references and OCR text, then read one item and its pages:

    bash
    curl -s "$MAILBOX_BOT_URL/v1/inbound-items?q=irs&limit=20" -H "Authorization: Bearer $MAILBOX_BOT_API_KEY"
curl -s "$MAILBOX_BOT_URL/v1/inbound-items/{id}" -H "Authorization: Bearer $MAILBOX_BOT_API_KEY"        # version, actions, quotes
curl -s "$MAILBOX_BOT_URL/v1/inbound-items/{id}/pages" -H "Authorization: Bearer $MAILBOX_BOT_API_KEY"  # OCR per page

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The install guide encourages connecting an AI client to a remote MCP server that can send physical mail, access mailbox contents, search OCR text, and retrieve inbound document context, but it does not prominently warn that sensitive documents, addresses, and mailbox metadata will be transmitted to and processed by a third-party remote service. In an agent-tooling context, this omission is risky because users may authorize broad access from coding assistants or autonomous agents without understanding the privacy and data-handling implications.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This manifest advertises capabilities that may process sensitive user data, including physical mailing addresses, forwarded documents, and webhook-delivered content, but it does not include any user-facing warning about privacy, data exposure, or downstream handling. For markdown and manifest-style descriptions, omitted warnings about behaviors that could affect user data or privacy should be flagged.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.